The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.

This paper focuses on a class of reinforcement learning (RL) algorithms, named integral RL (I-RL), that solve continuous-time (CT) nonlinear optimal control problems with input-affine system dynamics. First, we extend the concepts of exploration, integral temporal difference, and invariant admissibility to the target CT nonlinear system that is governed by a control policy plus a probing signal called an exploration. Then, we show input-to-state stability (ISS) and invariant admissibility of the closed-loop systems with the policies generated by integral policy iteration (I-PI) or invariantly admissible PI (IA-PI) method. Based on these, three online I-RL algorithms named explorized I-PI and integral Q -learning I, II are proposed, all of which generate the same convergent sequences as I-PI and IA-PI under the required excitation condition on the exploration. All the proposed methods are partially or completely model free, and can simultaneously explore the state space in a stable manner during the online learning processes. ISS, invariant admissibility, and convergence properties of the proposed methods are also investigated, and related with these, we show the design principles of the exploration for safe learning. Neural-network-based implementation methods for the proposed schemes are also presented in this paper. Finally, several numerical simulations are carried out to verify the effectiveness of the proposed methods.

In this study, the authors propose a blind spot reduction method in wavelet transform‐based time–frequency domain reflectometry (WTFDR) by using the Gaussian chirp as the mother wavelet. The blind spot is one of the intrinsic weak points in reflectometry and it means the overlapping ranges of the reference and the reflected signals when the fault is generated at a close distance. Owing to the blind spot, it is difficult to localise the close range fault. Thus, many researchers study the blind spot which is generated in various cables such as electric cable in flight, network cable and power cable. In this study, two methods are used to reduce the blind spot. Firstly, by using the linearity of a complex wavelet transform, the overlapped reference signal at the measured signal is separated and the blind spot is reduced by obtaining the difference of the moduli of the wavelet coefficients for the reference and the reflected signals. Secondly, by using the Gaussian chirp as the mother wavelet, which is designed by considering the characteristics of the cable, the wavelet analysis and the resolution of the WTFDR are improved. Finally, the computer simulations and the real experiments are performed to confirm the effectiveness and the accuracy of the proposed method.

This paper focuses on the integral reinforcement learning (I-RL) for input-affine continuous-time (CT) nonlinear systems where a known time-varying signal called an exploration is injected through the control input. First, we propose a modified I-RL method which effectively eliminates the effects of the explorations on the algorithm. Next, based on the result, an actor-critic I-RL technique is presented for the same nonlinear systems with completely unknown dynamics. Finally, the least-squares implementation method with the exact parameterizations is presented for each proposed one which can be solved under the given persistently exciting (PE) conditions. A simulation example is given to verify the effectiveness of the proposed methods.

In this paper, we propose a control method for stable grasp of dual-fingered robots with rigid hemispherical fingertips. The main contribution of the proposed approach is to lower the probability of the object slipping out of the fingertips as optimizing the angle of the grasping force. In addition, since the controller is allowed to use the tactile sensor, the shape of an object is not limited, as long as the contact point is positioned on the vicinity of smooth curvatures. We prove the stability analysis of the proposed controller via the Lyapunov direct method. Finally, we present simulation results to validate the effectiveness of the proposed approach.

We present a leader-follower-based adaptive formation control method for electrically driven nonholonomic mobile robots with limited information. First, an adaptive observer is developed under the condition that the velocity measurement is not available. With the proposed adaptive observer, the formation control part is designed to achieve the desired formation and guarantee the collision avoidance. In addition, neural network is employed to compensate the actuator saturation, and the projection algorithm is used to estimate the velocity information of the leader. It is shown, by using the Lyapunov theory, that all errors of the closed-loop system are uniformly ultimately bounded. Simulation results are presented to illustrate the performance of the proposed control system.

This brief proposes a simple control approach for a class of uncertain nonlinear systems with unknown time delays in strict-feedback form. That is, the dynamic surface control technique, which can solve the "explosion of complexity" problem in the backstepping design procedure, is extended to nonlinear systems with unknown time delays. The unknown time-delay effects are removed by using appropriate Lyapunov-Krasovskii functionals, and the uncertain nonlinear terms generated by this procedure as well as model uncertainties are approximated by the function approximation technique using neural networks. In addition, the bounds of external disturbances are estimated by the adaptive technique. From the Lyapunov stability theorem, we prove that all signals in the closed-loop system are semiglobally uniformly bounded. Finally, we present simulation results to validate the effectiveness of the proposed approach.

In this comment, we point out an error in [1], which will show that the main result of the paper cannot be generalized for nonlinearly parametric time-delay systems considered in [1]. In [1], the authors considered the problem of the adaptive control for a class of nonlinearly parametric time-delay systems and applied successfully the proposed approach to second-order nonlinear time-delay systems with the term x1(t - tau)x2(t - tau) used as simulation examples in Section VI. However, we show in this comment that the control approach presented in [1] cannot be generalized although it is realizable for nonlinear second-order time-delay systems with the term x1(t - tau ) x2(t - tau). In addition, we illustrate this error by one detail example. For simplicity, all the symbols in this comment are the same as those in [1].

In this paper, we propose a new robust output feedback control approach for flexible-joint electrically driven (FJED) robots via the observer dynamic surface design technique. The proposed method only requires position measurements of the FJED robots. To estimate the link and actuator velocity information of the FJED robots with model uncertainties, we develop an adaptive observer using self-recurrent wavelet neural networks (SRWNNs). The SRWNNs are used to approximate model uncertainties in both robot (link) dynamics and actuator dynamics, and all their weights are trained online. Based on the designed observer, the link position tracking controller using the estimated states is induced from the dynamic surface design procedure. Therefore, the proposed controller can be designed more simply than the observer backstepping controller. From the Lyapunov stability analysis, it is shown that all signals in a closed-loop adaptive system are uniformly ultimately bounded. Finally, the simulation results on a three-link FJED robot are presented to validate the good position tracking performance and robustness of the proposed control system against payload uncertainties and external disturbances.

A new method for the robust control of flexible-joint (FJ) robots with model uncertainties in both robot dynamics and actuator dynamics is proposed. The proposed control system is a combination of the adaptive dynamic surface control (DSC) technique and the self-recurrent wavelet neural network (SRWNN). The adaptive DSC technique provides the ability to overcome the "explosion of complexity" problem in backstepping controllers. The SRWNNs are used to observe the arbitrary model uncertainties of FJ robots, and all their weights are trained online. From the Lyapunov stability analysis, their adaptation laws are induced, and the uniformly ultimately boundedness of all signals in a closed-loop adaptive system is proved. Finally, simulation results for a three-link FJ robot are utilized to validate the good position tracking performance and robustness against payload uncertainties and external disturbances of the proposed control system.

A novel approach for navigation of cleaning robots in an unknown workspace is presented which includes a new map representation method and a complete coverage navigation mechanism. First, we discuss a triangular cell map representation which makes the cleaning robot navigate with a shorter path and increased flexibility than a rectangular cell map representation. Then, we propose the complete coverage navigation and map construction methods which enable the cleaning robot to navigate the complete workspace with no complete information about the environment. Finally, we evaluate the performance of our proposed triangular cell map via the existing distance-transform-based path planning method comparing to that of the rectangular cell map.